Statistical Modeling of Complex Backgrounds for Foreground Object Detection

Abstract

This paper addresses the problem of background modeling for foreground object detection in complex environments. A Bayesian framework that incorporates spectral, spatial, and temporal features to characterize the background appearance is proposed. Under this framework, the background is represented by the most significant and frequent features, i.e., the principal features, at each pixel. A Bayes decision rule is derived for background and foreground classification based on the statistics of principal features. Principal feature representation for both the static and dynamic background pixels is investigated. A novel learning method is proposed to adapt to both gradual and sudden "once-off" background changes. The convergence of the learning process is analyzed and a formula to select a proper learning rate is derived. Under the proposed framework, a novel algorithm for detecting foreground objects from complex environments is then established. It consists of change detection, change classification, foreground segmentation, and background maintenance. Experiments were conducted on image sequences containing targets of interest in a variety of environments, e.g., offices, public buildings, subway stations, campuses, parking lots, airports, and sidewalks. Good results of foreground detection were obtained. Quantitative evaluation and comparison with the existing method show that the proposed method provides much improved results.

Implementation of SIFT for detection of electronic waste

“…The key point of the test image has been matched with the background key point [13] of the template image as shown in The object which has been matched with the template image has been selected from the test image and converted into a binary image. Before the conversion of the binary image the test image on the whole gets converted into binary image [15]. Thus the converted binary image of both the test image and the detected object undergoes subtraction thus to obtain the area acquired by the detected object.…”

Background foreground segmentation with RGB-D Kinect data: An efficient combination of classifiers

“…On the contrary, the other sequences are conceived to highlight the impact of one particular issue to the algorithm under test that are marked as Fg; False Negative (FN) the fraction of Fg pixels that are marked as Bg; Total Error (TE) the total number of misclassified pixels, normalized with respect to the image size. Moreover, we consider also the similarity measure S defined in [32]. It is a non-linear measure that fuses FP and FN and it is close to 1 if detected Fg regions correspond to the real ones, otherwise its value is close to 0.…”

A Novel Approach in Video Scene Background Estimation

“…It performs quite well for both stationary and non-stationary backgrounds among the existing methods in [8]. We evaluate these methods using the quantitative measure used in [31]. If F is a detected region and G the corresponding "ground truth," then the similarity measure between regions F and G is defined as…”